Logistic_WGCNA_16
Computational Immunogenomics Core (CIG Core)
Center for Systems Immunology, University of Pittsburghsis186@pitt.edu
2024-04-30
1 Sample Metadata
| treatment | age_group | patient_id | sample | Sequence |
|---|---|---|---|---|
| 0 | 2 | 3 | 160008699_3_0_S5 | 1 |
| 1 | 2 | 3 | 160008699_3_8_S6 | 2 |
| 0 | 2 | 4 | 290001824_4_0_S7 | 3 |
| 1 | 2 | 4 | 290001824_4_8_S8 | 4 |
| 0 | 1 | 17 | 330001842_17_0_S31 | 5 |
| 1 | 1 | 17 | 330001842_17_8_S32 | 6 |
| 0 | 0 | 5 | 470009458_5_0_S9 | 7 |
| 1 | 0 | 5 | 470009458_5_4_S10 | 8 |
| 0 | 1 | 13 | 660009823_13_0_S25 | 9 |
| 1 | 1 | 13 | 660009823_13_8_S26 | 10 |
| 0 | 0 | 11 | 770004766_11_0_S21 | 11 |
| 1 | 0 | 11 | 770004766_11_8_S22 | 12 |
| 0 | 1 | 2 | 830001304_2_0_S3 | 13 |
| 1 | 1 | 2 | 830001304_2_4_S4 | 14 |
| 0 | 2 | 12 | 830002078_12_0_S23 | 15 |
| 1 | 2 | 12 | 830002078_12_8_S24 | 16 |
| 0 | 2 | 9 | 880001252_9_0_S17 | 17 |
| 1 | 2 | 9 | 880001252_9_8_S18 | 18 |
| 0 | 0 | 8 | 940004357_8_0_S15 | 19 |
| 1 | 0 | 8 | 940004357_8_8_S16 | 20 |
| 0 | 1 | 7 | 970002731_7_0_S13 | 21 |
| 1 | 1 | 7 | 970002731_7_4_S14 | 22 |
| 0 | 0 | 10 | 980007758_10_0_S19 | 23 |
| 1 | 0 | 10 | 980007758_10_8_S20 | 24 |
2 WGCNA result
Soft threshold = 16
soft threshold = 16
.
Modules = 29
29 modules in total
.
| Positive modules | Spearman correlation (p-value) |
|---|---|
| lightgreen (152 genes) | 0.14 (0.1) |
| Negative modules | Spearman correlation (p-value) |
|---|---|
| darkred (63 genes) | -0.12 (0.2) |
| midnightblue (303 genes) | -0.1 (0.2) |
3 Run LASSO on treatment-positive modules (Module lightgreen: 152 genes)
Alpha = 1
Nested cross validation
- outer loop method: leave-one-out
- inner loop method: leave-one-out
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold## Tuned lambda value:
## 0.04302683##
## Call: cv.glmnet(x = x, y = y, weights = ..2, foldid = foldid, alpha = tail(alphaSet, 1), family = ..1, penalty.factor = ..3)
##
## Measure: Binomial Deviance
##
## Lambda Index Measure SE Nonzero
## min 0.04303 41 1.042 0.2130 10
## 1se 0.08645 26 1.244 0.1541 7## Non-zero Coefficients:
## ENSG00000152894 ENSG00000084072 ENSG00000101057 ENSG00000173898 ENSG00000026559 ENSG00000058091 ENSG00000134532 ENSG00000112232 ENSG00000166833 ENSG000001685023.1 List of genes with non-zero coefficients (10 Genes)
| ensembl_gene_id | external_gene_name |
|---|---|
| ENSG00000026559 | KCNG1 |
| ENSG00000058091 | CDK14 |
| ENSG00000084072 | PPIE |
| ENSG00000101057 | MYBL2 |
| ENSG00000112232 | KHDRBS2 |
| ENSG00000134532 | SOX5 |
| ENSG00000152894 | PTPRK |
| ENSG00000166833 | NAV2 |
| ENSG00000168502 | MTCL1 |
| ENSG00000173898 | SPTBN2 |
3.2 AUC
3.3 Accuracy
## Reference
## Predicted 0 1
## 0 10 3
## 1 2 9## AUC Accuracy Balanced accuracy
## 0.7708333 0.7916667 0.79166673.4 TPM (pre-treatment (front) vs. post-treatment (back))
## 160008699_3_0_S5 160008699_3_8_S6 290001824_4_0_S7 290001824_4_8_S8
## KCNG1 0.65 0.94 0.89 1.28
## CDK14 6.49 5.21 7.49 8.77
## PPIE 21.15 16.44 17.39 17.77
## MYBL2 1.22 1.04 0.89 2.54
## KHDRBS2 0.52 0.46 0.31 0.48
## SOX5 0.04 0.17 1.80 0.37
## PTPRK 0.74 1.37 0.58 2.68
## NAV2 0.71 0.63 0.47 0.87
## MTCL1 0.30 0.44 0.48 0.34
## SPTBN2 0.65 0.05 0.36 0.19
## 330001842_17_0_S31 330001842_17_8_S32 470009458_5_0_S9
## KCNG1 0.51 0.93 0.55
## CDK14 3.21 5.54 4.61
## PPIE 12.59 10.86 11.87
## MYBL2 1.86 1.99 1.61
## KHDRBS2 0.38 0.41 0.25
## SOX5 0.63 0.36 1.62
## PTPRK 1.01 2.35 1.07
## NAV2 0.35 0.23 0.88
## MTCL1 0.41 0.43 0.32
## SPTBN2 0.24 0.09 0.27
## 470009458_5_4_S10 660009823_13_0_S25 660009823_13_8_S26
## KCNG1 1.03 0.22 0.13
## CDK14 5.35 3.87 8.58
## PPIE 12.52 12.76 5.29
## MYBL2 1.90 2.09 0.76
## KHDRBS2 0.27 0.30 0.20
## SOX5 2.58 0.89 0.19
## PTPRK 3.05 0.91 1.00
## NAV2 0.27 0.73 0.27
## MTCL1 0.27 0.23 0.31
## SPTBN2 0.21 0.20 0.28
## 770004766_11_0_S21 770004766_11_8_S22 830001304_2_0_S3 830001304_2_4_S4
## KCNG1 0.13 0.26 0.14 0.37
## CDK14 3.58 6.32 7.03 10.43
## PPIE 7.84 9.87 18.19 14.59
## MYBL2 0.80 1.07 1.46 0.99
## KHDRBS2 0.10 0.15 0.37 0.34
## SOX5 0.11 0.34 2.10 0.97
## PTPRK 0.44 0.76 1.95 2.48
## NAV2 0.06 0.05 1.10 0.65
## MTCL1 0.28 0.14 0.78 0.32
## SPTBN2 0.01 0.10 0.41 0.13
## 830002078_12_0_S23 830002078_12_8_S24 880001252_9_0_S17
## KCNG1 0.32 0.30 0.29
## CDK14 2.71 2.10 7.50
## PPIE 10.75 7.85 18.17
## MYBL2 1.09 0.16 0.95
## KHDRBS2 0.13 0.71 0.48
## SOX5 0.43 0.11 1.28
## PTPRK 0.60 0.59 1.38
## NAV2 0.51 0.26 0.29
## MTCL1 0.45 0.20 0.35
## SPTBN2 0.70 0.03 1.61
## 880001252_9_8_S18 940004357_8_0_S15 940004357_8_8_S16 970002731_7_0_S13
## KCNG1 0.48 0.09 0.60 0.22
## CDK14 5.82 3.65 6.42 5.13
## PPIE 11.21 13.71 8.37 10.27
## MYBL2 0.77 0.77 0.85 3.31
## KHDRBS2 0.36 0.16 0.40 0.19
## SOX5 0.53 0.42 0.71 0.30
## PTPRK 1.72 0.93 1.78 0.51
## NAV2 0.07 1.05 1.44 0.46
## MTCL1 0.26 0.16 0.37 0.28
## SPTBN2 0.19 0.07 0.36 0.11
## 970002731_7_4_S14 980007758_10_0_S19 980007758_10_8_S20
## KCNG1 1.09 1.01 1.19
## CDK14 6.11 5.42 6.72
## PPIE 9.80 16.09 12.64
## MYBL2 0.28 4.64 4.22
## KHDRBS2 0.75 0.39 0.58
## SOX5 0.28 0.58 0.70
## PTPRK 1.39 1.50 2.82
## NAV2 0.25 0.31 0.28
## MTCL1 0.59 0.32 0.44
## SPTBN2 0.69 0.44 0.063.5 Heatmap (Pre-treatment vs Post-treatment)
3.6 Heatmap for Log-FoldChange for each patient
## Warning: Setting row names on a tibble is deprecated.
## Setting row names on a tibble is deprecated.
4 Run LASSO on treatment-negative modules (Module darkred: 63 genes)
Alpha = 1
Nested cross validation
- outer loop method: leave-one-out
- inner loop method: k-fold; k = 4
- Didn’t find any non-zero coeffients when using leave-one-out for inner loop
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground## Tuned lambda value:
## 0.1464232##
## Call: cv.glmnet(x = x, y = y, weights = ..2, foldid = foldid, alpha = tail(alphaSet, 1), family = ..1, penalty.factor = ..3)
##
## Measure: Binomial Deviance
##
## Lambda Index Measure SE Nonzero
## min 0.1464 10 1.515 0.12399 4
## 1se 0.2225 1 1.524 0.07232 0## Non-zero Coefficients:
## ENSG00000279982 ENSG00000271550 ENSG00000272502 ENSG000001695194.1 AUC
4.2 Accuracy
##
## 0 1
## 0 12 0
## 1 0 12## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 1.000000e+00 1.000000e+00 8.575264e-01 1.000000e+00 5.000000e-01
## AccuracyPValue McnemarPValue
## 5.960464e-08 NaN4.3 List of genes with non-zero coefficients (4 genes)
| ensembl_gene_id | external_gene_name |
|---|---|
| ENSG00000169519 | METTL15 |
| ENSG00000271550 | BNIP3P11 |
| ENSG00000272502 | ENSG00000272502 |
| ENSG00000279982 | ENSG00000279982 |
4.4 TPM (pre-treatment (front) vs. post-treatment (back))
## 160008699_3_0_S5 160008699_3_8_S6 290001824_4_0_S7
## METTL15 5.35 2.49 3.64
## BNIP3P11 2.31 0.57 2.81
## ENSG00000272502 0.69 1.36 2.28
## ENSG00000279982 0.17 0.13 0.25
## 290001824_4_8_S8 330001842_17_0_S31 330001842_17_8_S32
## METTL15 3.16 1.91 2.29
## BNIP3P11 2.88 1.74 0.88
## ENSG00000272502 1.16 0.76 0.26
## ENSG00000279982 0.29 0.17 0.16
## 470009458_5_0_S9 470009458_5_4_S10 660009823_13_0_S25
## METTL15 1.98 1.63 3.71
## BNIP3P11 0.84 0.55 3.26
## ENSG00000272502 1.03 0.45 0.74
## ENSG00000279982 0.11 0.12 0.58
## 660009823_13_8_S26 770004766_11_0_S21 770004766_11_8_S22
## METTL15 0.76 1.05 1.83
## BNIP3P11 0.38 0.54 0.91
## ENSG00000272502 0.38 0.37 0.68
## ENSG00000279982 0.06 0.06 0.05
## 830001304_2_0_S3 830001304_2_4_S4 830002078_12_0_S23
## METTL15 4.07 2.69 2.33
## BNIP3P11 2.34 1.15 1.56
## ENSG00000272502 1.43 0.58 0.70
## ENSG00000279982 0.33 0.21 0.28
## 830002078_12_8_S24 880001252_9_0_S17 880001252_9_8_S18
## METTL15 2.01 3.53 2.06
## BNIP3P11 1.27 3.41 0.89
## ENSG00000272502 0.65 1.53 0.54
## ENSG00000279982 0.12 0.38 0.15
## 940004357_8_0_S15 940004357_8_8_S16 970002731_7_0_S13
## METTL15 1.91 1.64 2.7
## BNIP3P11 1.01 0.69 1.1
## ENSG00000272502 0.76 0.45 0.4
## ENSG00000279982 0.18 0.23 0.2
## 970002731_7_4_S14 980007758_10_0_S19 980007758_10_8_S20
## METTL15 1.61 2.80 2.05
## BNIP3P11 1.43 2.17 2.32
## ENSG00000272502 0.45 1.29 0.75
## ENSG00000279982 0.10 0.28 0.144.5 Heatmap (Pre-treatment vs Post-treatment)
4.6 Heatmap for Log-FoldChange for each patient
## Warning: Setting row names on a tibble is deprecated.
## Setting row names on a tibble is deprecated.
5 Run LASSO on treatment-negative module (Module midnightblue: 303 genes)
Alpha = 1
Nested cross validation
- outer loop method: leave-one-out
- inner loop method: k-fold; k = 4
- Didn’t find any non-zero coeffients when using leave-one-out for inner loop
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground
## Warning in lognet(xd, is.sparse, ix, jx, y, weights, offset, alpha, nobs, : one
## multinomial or binomial class has fewer than 8 observations; dangerous ground## Tuned lambda value:
## 0.2217997##
## Call: cv.glmnet(x = x, y = y, weights = ..2, foldid = foldid, alpha = tail(alphaSet, 1), family = ..1, penalty.factor = ..3)
##
## Measure: Binomial Deviance
##
## Lambda Index Measure SE Nonzero
## min 0.2218 2 1.509 0.09580 1
## 1se 0.2324 1 1.509 0.09087 0## Non-zero Coefficients:
## ENSG000001860735.1 AUC
5.2 Accuracy
##
## 0 1
## 0 12 0
## 1 0 12## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 1.000000e+00 1.000000e+00 8.575264e-01 1.000000e+00 5.000000e-01
## AccuracyPValue McnemarPValue
## 5.960464e-08 NaN5.3 List of genes with non-zero coefficients (1 gene)
| ensembl_gene_id | external_gene_name |
|---|---|
| ENSG00000186073 | CDIN1 |
5.4 TPM (pre-treatment (front) vs. post-treatment (back))
## 160008699_3_0_S5 160008699_3_8_S6 290001824_4_0_S7 290001824_4_8_S8
## CDIN1 1.14 1.35 2.48 1.72
## 330001842_17_0_S31 330001842_17_8_S32 470009458_5_0_S9 470009458_5_4_S10
## CDIN1 1.36 1.58 1.04 0.96
## 660009823_13_0_S25 660009823_13_8_S26 770004766_11_0_S21
## CDIN1 1.94 0.58 0.74
## 770004766_11_8_S22 830001304_2_0_S3 830001304_2_4_S4 830002078_12_0_S23
## CDIN1 0.52 2.13 1.61 1.24
## 830002078_12_8_S24 880001252_9_0_S17 880001252_9_8_S18 940004357_8_0_S15
## CDIN1 0.81 1.95 0.77 1.05
## 940004357_8_8_S16 970002731_7_0_S13 970002731_7_4_S14 980007758_10_0_S19
## CDIN1 0.72 1.43 0.83 1.74
## 980007758_10_8_S20
## CDIN1 1.155.5 Heatmap (Pre-treatment vs Post-treatment)
5.6 Heatmap for Log-FoldChange for each patient
## Warning: Setting row names on a tibble is deprecated.
## Setting row names on a tibble is deprecated.
6 Final model
6.1 Final Lasso nested cv (Total 15 genes)
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold
## Warning: Option grouped=FALSE enforced in cv.glmnet, since < 3 observations per
## fold## Tuned lambda value:
## 0.02243423##
## Call: cv.glmnet(x = x, y = y, weights = ..2, foldid = foldid, alpha = tail(alphaSet, 1), family = ..1, penalty.factor = ..3)
##
## Measure: Binomial Deviance
##
## Lambda Index Measure SE Nonzero
## min 0.02243 28 0.9762 0.3644 10
## 1se 0.19064 5 1.2901 0.0605 2## Non-zero Coefficients:
## ENSG00000152894 ENSG00000186073 ENSG00000112232 ENSG00000173898 ENSG00000058091 ENSG00000084072 ENSG00000166833 ENSG00000101057 ENSG00000271550 ENSG000001345326.1.1 AUC
6.1.2 Accuracy of nested cv
## Reference
## Predicted 0 1
## 0 10 3
## 1 2 9## AUC Accuracy Balanced accuracy
## 0.8611111 0.7916667 0.79166676.2 Final model (10 genes)
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred##
## Call:
## glm(formula = formula_str, family = binomial, data = data.frame(final_model_matrix))
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -6.098e+00 1.006e+05 0 1
## ENSG00000152894 1.064e+01 2.610e+05 0 1
## ENSG00000186073 -2.001e+01 1.661e+05 0 1
## ENSG00000112232 2.255e+01 1.773e+05 0 1
## ENSG00000173898 -3.164e+01 2.157e+05 0 1
## ENSG00000058091 2.196e+01 2.018e+05 0 1
## ENSG00000084072 -1.369e+00 1.491e+05 0 1
## ENSG00000166833 -3.067e+00 1.208e+05 0 1
## ENSG00000101057 -7.221e-01 2.505e+05 0 1
## ENSG00000271550 8.555e-01 2.179e+05 0 1
## ENSG00000134532 2.729e+00 1.245e+05 0 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 3.3271e+01 on 23 degrees of freedom
## Residual deviance: 3.8444e-10 on 13 degrees of freedom
## AIC: 22
##
## Number of Fisher Scoring iterations: 256.2.1 Check correlation between each feature
6.3 Check complete separation (perfect prediction)
## Implementation: ROI | Solver: lpsolve
## Separation: TRUE
## Existence of maximum likelihood estimates
## (Intercept) ENSG00000152894 ENSG00000186073 ENSG00000112232 ENSG00000173898
## -Inf Inf -Inf Inf -Inf
## ENSG00000058091 ENSG00000084072 ENSG00000166833 ENSG00000101057 ENSG00000271550
## Inf -Inf Inf -Inf -Inf
## ENSG00000134532
## -Inf
## 0: finite value, Inf: infinity, -Inf: -infinity6.4 Method 1: Bayes
## bayesglm(formula = formula_str, family = binomial(link = "logit"),
## data = as.data.frame(final_model_matrix))
## coef.est coef.se
## (Intercept) -0.12 0.82
## ENSG00000152894 1.90 1.05
## ENSG00000186073 -0.90 0.92
## ENSG00000112232 0.98 0.75
## ENSG00000173898 -0.73 0.85
## ENSG00000058091 0.72 0.78
## ENSG00000084072 -0.46 0.81
## ENSG00000166833 -0.38 0.67
## ENSG00000101057 -0.49 0.78
## ENSG00000271550 -0.46 0.84
## ENSG00000134532 -0.42 0.74
## ---
## n = 24, k = 11
## residual deviance = 4.4, null deviance = 33.3 (difference = 28.9)##
## Call: bayesglm(formula = formula_str, family = binomial(link = "logit"),
## data = as.data.frame(final_model_matrix), method = "detect_separation")
##
## Coefficients:
## (Intercept) ENSG00000152894 ENSG00000186073 ENSG00000112232
## -0.1212 1.9042 -0.9044 0.9826
## ENSG00000173898 ENSG00000058091 ENSG00000084072 ENSG00000166833
## -0.7303 0.7199 -0.4559 -0.3832
## ENSG00000101057 ENSG00000271550 ENSG00000134532
## -0.4893 -0.4556 -0.4180
##
## Degrees of Freedom: 23 Total (i.e. Null); 13 Residual
## Null Deviance: 33.27
## Residual Deviance: 4.371 AIC: 26.376.4.1 AUC:bayes
6.5 Method 2: Firth’s Bias-Reduced Logistic Regression
Firth’s bias reduction method, equivalent to penalization of the log-likelihood
## logistf(formula = formula_str, data = as.data.frame(final_model_matrix))
##
## Model fitted by Penalized ML
## Coefficients:
## coef se(coef) lower 0.95 upper 0.95 Chisq
## (Intercept) -0.12162486 0.4778238 -1.951730 1.132856 0.04654081
## ENSG00000152894 0.80908839 0.9235939 -1.807387 5.566714 0.56450734
## ENSG00000186073 -0.38336802 0.8365246 -3.149846 1.940889 0.15791745
## ENSG00000112232 0.75311207 0.8088889 -1.108937 4.582622 0.68644923
## ENSG00000173898 -0.71874510 0.6776823 -4.860134 1.561141 0.77934305
## ENSG00000058091 0.93825921 0.7412681 -1.345513 4.437082 0.91025159
## ENSG00000084072 -0.15907838 0.7356271 -2.756363 1.884979 0.03434081
## ENSG00000166833 -0.41668886 0.4749537 -2.084143 1.162984 0.56991526
## ENSG00000101057 -0.64074898 0.7742647 -4.848279 1.731083 0.47489122
## ENSG00000271550 -0.19599018 0.9240849 -3.468708 2.428395 0.03374195
## ENSG00000134532 -0.09648449 0.6567023 -3.243360 1.871623 0.01625704
## p method
## (Intercept) 0.8291957 2
## ENSG00000152894 0.4524498 2
## ENSG00000186073 0.6910811 2
## ENSG00000112232 0.4073748 2
## ENSG00000173898 0.3773421 2
## ENSG00000058091 0.3400477 2
## ENSG00000084072 0.8529838 2
## ENSG00000166833 0.4502926 2
## ENSG00000101057 0.4907455 2
## ENSG00000271550 0.8542568 2
## ENSG00000134532 0.8985422 2
##
## Method: 1-Wald, 2-Profile penalized log-likelihood, 3-None
##
## Likelihood ratio test=16.91808 on 10 df, p=0.07619644, n=24
## Wald test = 11.02228 on 10 df, p = 0.3557845## logistf(formula = formula_str, data = as.data.frame(final_model_matrix),
## method = "detect_separation")
## Model fitted by Penalized ML
## Confidence intervals and p-values by Profile Likelihood
##
## Coefficients:
## (Intercept) ENSG00000152894 ENSG00000186073 ENSG00000112232 ENSG00000173898
## -0.12162486 0.80908839 -0.38336802 0.75311207 -0.71874510
## ENSG00000058091 ENSG00000084072 ENSG00000166833 ENSG00000101057 ENSG00000271550
## 0.93825921 -0.15907838 -0.41668886 -0.64074898 -0.19599018
## ENSG00000134532
## -0.09648449
##
## Likelihood ratio test=16.91808 on 10 df, p=0.07619644, n=24## [1] "AUC (test): 1"
## [1] "Accuracy (test): 1"Check direction of each gene in two models, all the same
7 Final genes list (Total 10 genes)
| Modules (size) | Module correlation to treatment | Genes selected by lasso |
|---|---|---|
| lightgreen (152 genes) | Positive | 8 |
| darkred (63 genes) | Negative | 1 |
| midnightblue (303 genes) | Negative | 1 |
| ensembl_gene_id | external_gene_name | |
|---|---|---|
| 1 | ENSG00000058091 | CDK14 |
| 2 | ENSG00000084072 | PPIE |
| 3 | ENSG00000101057 | MYBL2 |
| 4 | ENSG00000112232 | KHDRBS2 |
| 5 | ENSG00000134532 | SOX5 |
| 6 | ENSG00000152894 | PTPRK |
| 7 | ENSG00000166833 | NAV2 |
| 8 | ENSG00000173898 | SPTBN2 |
| 9 | ENSG00000271550 | BNIP3P11 |
| 10 | ENSG00000186073 | CDIN1 |
7.1 Heatmap (Pre-treatment vs Post-treatment)
7.2 Heatmap for Log-FoldChange for each patient
## Warning: Setting row names on a tibble is deprecated.
## Setting row names on a tibble is deprecated.
8 Pathway Analysis ORA
Reactome
.
KEGG
.